Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to actions and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frye
    -0.57
     Sett
    -0.56
    brochen
    -0.54
    posia
    -0.54
    drawLine
    -0.53
    ြ
    -0.52
     Aff
    -0.51
     tuyến
    -0.51
    thesis
    -0.51
    DrawerToggle
    -0.51
    POSITIVE LOGITS
     kasarigan
    0.96
     coloured
    0.81
     actions
    0.81
     Actions
    0.76
    actions
    0.72
    mybatisplus
    0.72
     OMITBAD
    0.71
     Coloured
    0.69
     ACTIONS
    0.69
    coloured
    0.68
    Act Density 0.030%

    No Known Activations